Timezone: »

 
Workshop
Automatic Machine Learning (AutoML 2017)
Joaquin Vanschoren · Roman Garnett

Wed Aug 09 03:30 PM -- 12:30 AM (PDT) @ C4.9
Event URL: http://icml2017.automl.org »

Machine learning has achieved considerable successes in recent years and an ever-growing number of disciplines rely on it. However, this success crucially relies on human machine learning experts, who select appropriate features, workflows, machine learning paradigms, algorithms, and their hyperparameters. As the complexity of these tasks is often beyond non-experts, the rapid growth of machine learning applications has created a demand for off-the-shelf machine learning methods that can be used easily and without expert knowledge. We call the resulting research area that targets progressive automation of machine learning AutoML.

Author Information

Joaquin Vanschoren (TU Eindhoven / OpenML)

Joaquin Vanschoren is an assistant professor at the Eindhoven University of Technology. His research focuses on automated machine learning and meta-learning. He has received the Dutch Data prize in 2016 and an Amazon Research Award in 2019. He is a regular invited speaker at international conferences and workshops (including NeurIPS, ICML, the UN summit on AI for Good, and the Dutch eScience Symposium), and regularly gives talks at companies (e.g. Amazon Cambridge, Amazon Berlin, IBM New York). He also gives regular tutorials on meta-learning (including at NeurIPS 2018 and the ACDL summer school). He is co-editor and co-author of the reference book on Automated Machine Learning. He co-organizes the Automated Machine Learning workshop series at ICML and the meta-learning workshop series at NeurIPS. He was also general chair, program chair, and/or demo chair at European machine learning conferences. He also founded and runs OpenML.org, a popular open science platform for machine learning, with over 150.000 yearly users worldwide. His work has been mentioned in Science Magazine, ACM Explorations, KDnuggets, and Open Science Radio.

Roman Garnett (Washington University in St. Louis)

More from the Same Authors